Hugging Face's logo

vermoney
/
cdc1a8da-3025-4663-a070-219f81140542

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
cdc1a8da-3025-4663-a070-219f81140542
File size: 3,264 Bytes 
dc384ac
 
 
5ec104f
dc384ac
5ec104f
dc384ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6d75853
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ec104f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc384ac
 
 
 
 
 
 
 
 
 
 
 
 
 
5ec104f
dc384ac
 
 
 
5ec104f
dc384ac
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0020479213598197828,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.82640453273261e-05,
      "eval_loss": 11.5,
      "eval_runtime": 64.3905,
      "eval_samples_per_second": 95.79,
      "eval_steps_per_second": 47.895,
      "step": 1
    },
    {
      "epoch": 0.00020479213598197828,
      "grad_norm": 2.1372459741542116e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00040958427196395656,
      "grad_norm": 1.6634101484669372e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0005461123626186088,
      "eval_loss": 11.5,
      "eval_runtime": 64.1319,
      "eval_samples_per_second": 96.177,
      "eval_steps_per_second": 48.088,
      "step": 8
    },
    {
      "epoch": 0.0006143764079459349,
      "grad_norm": 2.0664107069023885e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0008191685439279131,
      "grad_norm": 2.0053583284607157e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0010239606799098914,
      "grad_norm": 2.8997801564401016e-05,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0010922247252372176,
      "eval_loss": 11.5,
      "eval_runtime": 63.3764,
      "eval_samples_per_second": 97.323,
      "eval_steps_per_second": 48.662,
      "step": 16
    },
    {
      "epoch": 0.0012287528158918697,
      "grad_norm": 2.1670148271368816e-05,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0014335449518738481,
      "grad_norm": 3.1137569749262184e-05,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.0016383370878558263,
      "grad_norm": 1.8660140995052643e-05,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0016383370878558263,
      "eval_loss": 11.5,
      "eval_runtime": 62.6205,
      "eval_samples_per_second": 98.498,
      "eval_steps_per_second": 49.249,
      "step": 24
    },
    {
      "epoch": 0.0018431292238378046,
      "grad_norm": 2.88584142253967e-05,
      "learning_rate": 5.449673790581611e-06,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.0020479213598197828,
      "grad_norm": 2.4676324756001122e-05,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1246752768000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}